Sakedo
/

Behemoth-123b-Q4-mlx

4-bit precision

Model card Files Files and versions

This is a Q4 MLX conversion of Behemoth 1.2

Downloads last month: 4

Safetensors

Model size

23B params

Tensor type

F16

·

U32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support